scikit-learn · jeremiedbb · Mar 29, 2022 · Dec 2, 2019 · Dec 13, 2019 · Dec 16, 2019
diff --git a/doc/modules/classes.rst b/doc/modules/classes.rst
@@ -657,6 +657,7 @@ Plotting
    :toctree: generated/
    :template: class.rst
 
+   inspection.DecisionBoundaryDisplay
    inspection.PartialDependenceDisplay
 
 .. autosummary::

diff --git a/doc/visualizations.rst b/doc/visualizations.rst
@@ -96,6 +96,7 @@ Display Objects
 
    calibration.CalibrationDisplay
    inspection.PartialDependenceDisplay
+   inspection.DecisionBoundaryDisplay
    metrics.ConfusionMatrixDisplay
    metrics.DetCurveDisplay
    metrics.PrecisionRecallDisplay

diff --git a/doc/whats_new/v1.1.rst b/doc/whats_new/v1.1.rst
@@ -534,6 +534,10 @@ Changelog
 :mod:`sklearn.inspection`
 .........................
 
+- |Feature| Add a display to plot the boundary decision of a classifier by
+  using the method :func:`inspection.DecisionBoundaryDisplay.from_estimator`.
+  :pr:`16061` by `Thomas Fan`_.
+
 - |Enhancement| In
   :meth:`~sklearn.inspection.PartialDependenceDisplay.from_estimator` and
   :meth:`~sklearn.inspection.PartialDependenceDisplay.from_predictions`, allow

diff --git a/examples/classification/plot_classifier_comparison.py b/examples/classification/plot_classifier_comparison.py
@@ -40,8 +40,7 @@
 from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
 from sklearn.naive_bayes import GaussianNB
 from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
-
-h = 0.02  # step size in the mesh
+from sklearn.inspection import DecisionBoundaryDisplay
 
 names = [
     "Nearest Neighbors",
@@ -95,7 +94,6 @@
 
     x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5
     y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
-    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
 
     # just plot the dataset first
     cm = plt.cm.RdBu
@@ -109,8 +107,8 @@
     ax.scatter(
         X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6, edgecolors="k"
     )
-    ax.set_xlim(xx.min(), xx.max())
-    ax.set_ylim(yy.min(), yy.max())
+    ax.set_xlim(x_min, x_max)
+    ax.set_ylim(y_min, y_max)
     ax.set_xticks(())
     ax.set_yticks(())
     i += 1
@@ -120,17 +118,9 @@
         ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
         clf.fit(X_train, y_train)
         score = clf.score(X_test, y_test)
-
-        # Plot the decision boundary. For that, we will assign a color to each
-        # point in the mesh [x_min, x_max]x[y_min, y_max].
-        if hasattr(clf, "decision_function"):
-            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
-        else:
-            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
-
-        # Put the result into a color plot
-        Z = Z.reshape(xx.shape)
-        ax.contourf(xx, yy, Z, cmap=cm, alpha=0.8)
+        DecisionBoundaryDisplay.from_estimator(
+            clf, X, cmap=cm, alpha=0.8, ax=ax, eps=0.5
+        )
 
         # Plot the training points
         ax.scatter(
@@ -146,15 +136,15 @@
             alpha=0.6,
         )
 
-        ax.set_xlim(xx.min(), xx.max())
-        ax.set_ylim(yy.min(), yy.max())
+        ax.set_xlim(x_min, x_max)
+        ax.set_ylim(y_min, y_max)
         ax.set_xticks(())
         ax.set_yticks(())
         if ds_cnt == 0:
             ax.set_title(name)
         ax.text(
-            xx.max() - 0.3,
-            yy.min() + 0.3,
+            x_max - 0.3,
+            y_min + 0.3,
             ("%.2f" % score).lstrip("0"),
             size=15,
             horizontalalignment="right",

diff --git a/examples/cluster/plot_inductive_clustering.py b/examples/cluster/plot_inductive_clustering.py
@@ -23,12 +23,12 @@
 # Authors: Chirag Nagpal
 #          Christos Aridas
 
-import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.base import BaseEstimator, clone
 from sklearn.cluster import AgglomerativeClustering
 from sklearn.datasets import make_blobs
 from sklearn.ensemble import RandomForestClassifier
+from sklearn.inspection import DecisionBoundaryDisplay
 from sklearn.utils.metaestimators import available_if
 from sklearn.utils.validation import check_is_fitted
 
@@ -116,19 +116,14 @@ def plot_scatter(X, color, alpha=0.5):
 probable_clusters = inductive_learner.predict(X_new)
 
 
-plt.subplot(133)
+ax = plt.subplot(133)
 plot_scatter(X, cluster_labels)
 plot_scatter(X_new, probable_clusters)
 
 # Plotting decision regions
-x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1), np.arange(y_min, y_max, 0.1))
-
-Z = inductive_learner.predict(np.c_[xx.ravel(), yy.ravel()])
-Z = Z.reshape(xx.shape)
-
-plt.contourf(xx, yy, Z, alpha=0.4)
+DecisionBoundaryDisplay.from_estimator(
+    inductive_learner, X, response_method="predict", alpha=0.4, ax=ax
+)
 plt.title("Classify unknown instances")
 
 plt.show()
diff --git a/examples/ensemble/plot_adaboost_twoclass.py b/examples/ensemble/plot_adaboost_twoclass.py
@@ -27,6 +27,7 @@
 from sklearn.ensemble import AdaBoostClassifier
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.datasets import make_gaussian_quantiles
+from sklearn.inspection import DecisionBoundaryDisplay
 
 
 # Construct dataset
@@ -53,16 +54,18 @@
 plt.figure(figsize=(10, 5))
 
 # Plot the decision boundaries
-plt.subplot(121)
-x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-xx, yy = np.meshgrid(
-    np.arange(x_min, x_max, plot_step), np.arange(y_min, y_max, plot_step)
+ax = plt.subplot(121)
+disp = DecisionBoundaryDisplay.from_estimator(
+    bdt,
+    X,
+    cmap=plt.cm.Paired,
+    response_method="predict",
+    ax=ax,
+    xlabel="x",
+    ylabel="y",
 )
-
-Z = bdt.predict(np.c_[xx.ravel(), yy.ravel()])
-Z = Z.reshape(xx.shape)
-cs = plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
+x_min, x_max = disp.xx0.min(), disp.xx0.max()
+y_min, y_max = disp.xx1.min(), disp.xx1.max()
 plt.axis("tight")
 
 # Plot the training points
@@ -80,8 +83,7 @@
 plt.xlim(x_min, x_max)
 plt.ylim(y_min, y_max)
 plt.legend(loc="upper right")
-plt.xlabel("x")
-plt.ylabel("y")
+
 plt.title("Decision Boundary")
 
 # Plot the two-class decision scores

diff --git a/examples/ensemble/plot_voting_decision_regions.py b/examples/ensemble/plot_voting_decision_regions.py
@@ -25,14 +25,14 @@
 
 from itertools import product
 
-import numpy as np
 import matplotlib.pyplot as plt
 
 from sklearn import datasets
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.svm import SVC
 from sklearn.ensemble import VotingClassifier
+from sklearn.inspection import DecisionBoundaryDisplay
 
 # Loading some example data
 iris = datasets.load_iris()
@@ -55,22 +55,15 @@
 eclf.fit(X, y)
 
 # Plotting decision regions
-x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-xx, yy = np.meshgrid(np.a
EED3
range(x_min, x_max, 0.1), np.arange(y_min, y_max, 0.1))
-
 f, axarr = plt.subplots(2, 2, sharex="col", sharey="row", figsize=(10, 8))
-
 for idx, clf, tt in zip(
     product([0, 1], [0, 1]),
     [clf1, clf2, clf3, eclf],
     ["Decision Tree (depth=4)", "KNN (k=7)", "Kernel SVM", "Soft Voting"],
 ):
-
-    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
-    Z = Z.reshape(xx.shape)
-
-    axarr[idx[0], idx[1]].contourf(xx, yy, Z, alpha=0.4)
+    DecisionBoundaryDisplay.from_estimator(
+        clf, X, alpha=0.4, ax=axarr[idx[0], idx[1]], response_method="predict"
+    )
     axarr[idx[0], idx[1]].scatter(X[:, 0], X[:, 1], c=y, s=20, edgecolor="k")
     axarr[idx[0], idx[1]].set_title(tt)
 

diff --git a/examples/linear_model/plot_iris_logistic.py b/examples/linear_model/plot_iris_logistic.py
@@ -15,10 +15,10 @@
 # Modified for documentation by Jaques Grobler
 # License: BSD 3 clause
 
-import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.linear_model import LogisticRegression
 from sklearn import datasets
+from sklearn.inspection import DecisionBoundaryDisplay
 
 # import some data to play with
 iris = datasets.load_iris()
@@ -29,26 +29,24 @@
 logreg = LogisticRegression(C=1e5)
 logreg.fit(X, Y)
 
-# Plot the decision boundary. For that, we will assign a color to each
-# point in the mesh [x_min, x_max]x[y_min, y_max].
-x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5
-y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
-h = 0.02  # step size in the mesh
-xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
-Z = logreg.predict(np.c_[xx.ravel(), yy.ravel()])
-
-# Put the result into a color plot
-Z = Z.reshape(xx.shape)
-plt.figure(1, figsize=(4, 3))
-plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)
+_, ax = plt.subplots(figsize=(4, 3))
+DecisionBoundaryDisplay.from_estimator(
+    logreg,
+    X,
+    cmap=plt.cm.Paired,
+    ax=ax,
+    response_method="predict",
+    plot_method="pcolormesh",
+    shading="auto",
+    xlabel="Sepal length",
+    ylabel="Sepal width",
+    eps=0.5,
+)
 
 # Plot also the training points
 plt.scatter(X[:, 0], X[:, 1], c=Y, edgecolors="k", cmap=plt.cm.Paired)
-plt.xlabel("Sepal length")
-plt.ylabel("Sepal width")
 
-plt.xlim(xx.min(), xx.max())
-plt.ylim(yy.min(), yy.max())
+
 plt.xticks(())
 plt.yticks(())
 

diff --git a/examples/linear_model/plot_logistic_multinomial.py b/examples/linear_model/plot_logistic_multinomial.py
@@ -16,6 +16,7 @@
 import matplotlib.pyplot as plt
 from sklearn.datasets import make_blobs
 from sklearn.linear_model import LogisticRegression
+from sklearn.inspection import DecisionBoundaryDisplay
 
 # make 3-class dataset for classification
 centers = [[-5, 0], [0, 1.5], [5, -1]]
@@ -31,19 +32,10 @@
     # print the training scores
     print("training score : %.3f (%s)" % (clf.score(X, y), multi_class))
 
-    # create a mesh to plot in
-    h = 0.02  # step size in the mesh
-    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
-
-    # Plot the decision boundary. For that, we will assign a color to each
-    # point in the mesh [x_min, x_max]x[y_min, y_max].
-    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
-    # Put the result into a color plot
-    Z = Z.reshape(xx.shape)
-    plt.figure()
-    plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
+    _, ax = plt.subplots()
+    DecisionBoundaryDisplay.from_estimator(
+        clf, X, response_method="predict", cmap=plt.cm.Paired, ax=ax
+    )
     plt.title("Decision surface of LogisticRegression (%s)" % multi_class)
     plt.axis("tight")
 

diff --git a/examples/linear_model/plot_sgd_iris.py b/examples/linear_model/plot_sgd_iris.py
@@ -13,6 +13,7 @@
 import matplotlib.pyplot as plt
 from sklearn import datasets
 from sklearn.linear_model import SGDClassifier
+from sklearn.inspection import DecisionBoundaryDisplay
 
 # import some data to play with
 iris = datasets.load_iris()
@@ -35,21 +36,17 @@
 std = X.std(axis=0)
 X = (X - mean) / std
 
-h = 0.02  # step size in the mesh
-
 clf = SGDClassifier(alpha=0.001, max_iter=100).fit(X, y)
-
-# create a mesh to plot in
-x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
-
-# Plot the decision boundary. For that, we will assign a color to each
-# point in the mesh [x_min, x_max]x[y_min, y_max
713D
].
-Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
-# Put the result into a color plot
-Z = Z.reshape(xx.shape)
-cs = plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
+ax = plt.gca()
+DecisionBoundaryDisplay.from_estimator(
+    clf,
+    X,
+    cmap=plt.cm.Paired,
+    ax=ax,
+    response_method="predict",
+    xlabel=iris.feature_names[0],
+    ylabel=iris.feature_names[1],
+)
 plt.axis("tight")
 
 # Plot also the training points